The primary goal of this project is to develop a novel approach for adapting GANs to new domains using only a single target domain example. Traditional domain adaptation techniques often require a significant amount of labeled data from the target domain, which can be impractical in many real-world scenarios.
- We have prepared the scripts to train new models
- For training model without entities,
sh scripts/train_OSGA.sh - For training model with entities,
sh scripts/train_GOGA.sh - For inference,
sh scripts/inference.sh
- For training model without entities,
Report.pdf is provided to readers.